Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef1cfa3c0805e9b43a22e55c4c4ea77b82f289af7f5665211aa05ca8d475eff4
+oid sha256:ab311ff42dd1208e5c2963258415c6b725fe9aee09ecc86f61c87f400c0727df
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2581b4ab8391af36bff81bca856eb7a09a2480fa58262cb4f28fd067606d2c97
+oid sha256:f50163154eaa787c6bc14155cd6685bcd042302dfd357522c5ad779553a8e076
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bf1d7f99720789de6c7307398b026d75628c08c81d3b63e5987186854494d6e
+oid sha256:10fb699f8dddba63a61193a3379a229f85bbc1cdda93264e6ad8b56cdcfae6be
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03219814241486068,
+  "epoch": 0.06439628482972136,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 15.938,
       "eval_steps_per_second": 7.969,
       "step": 10
+    },
+    {
+      "epoch": 0.03715170278637771,
+      "grad_norm": 0.5686100721359253,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.5611,
+      "step": 15
+    },
+    {
+      "epoch": 0.04953560371517028,
+      "grad_norm": 0.5406749248504639,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.4431,
+      "step": 20
+    },
+    {
+      "epoch": 0.04953560371517028,
+      "eval_loss": 1.4391350746154785,
+      "eval_runtime": 10.6788,
+      "eval_samples_per_second": 15.919,
+      "eval_steps_per_second": 7.96,
+      "step": 20
+    },
+    {
+      "epoch": 0.06191950464396285,
+      "grad_norm": 0.6904301047325134,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.3865,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2382588127739904.0,
+  "total_flos": 4765176255479808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null